wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Include examples in type checking

Browse Source 
Remove `examples/` from the `pyrightconfig.json` ignore list and fix
the resulting type errors across all example files. Common fixes:

- Required API keys: `os.getenv("X")` -> `os.environ["X"]` so the
  return type is `str` rather than `str | None`, and misconfiguration
  fails fast.
- Narrow `LLMContextMessage` union members with `isinstance(..., dict)`
  before dict-style access.
- `assert isinstance(params.llm, ...)` before calling service-specific
  methods that aren't on the base `LLMService`.
- Guard optional frame fields (e.g. `LLMSearchResponseFrame.search_result`)
  before use.
This commit is contained in:
Mark Backman
2026-04-20 15:50:49 -04:00
parent 103ced1eaa
commit 58a17c7b1b
293 changed files with 884 additions and 1006 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
examples/voice/voice-aicoustics.py
View File

@@ -73,17 +73,17 @@ transport_params = {
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
api_key=os.environ["CARTESIA_API_KEY"],
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
api_key=os.environ["OPENAI_API_KEY"],
settings=OpenAILLMService.Settings(
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
),

6
examples/voice/voice-assemblyai-turn-detection.py
View File

@@ -91,7 +91,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = AssemblyAISTTService(
api_key=os.getenv("ASSEMBLYAI_API_KEY"),
api_key=os.environ["ASSEMBLYAI_API_KEY"],
vad_force_turn_endpoint=False, # Use AssemblyAI's built-in turn detection
settings=AssemblyAISTTService.Settings(
model="u3-rt-pro",
@@ -106,14 +106,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
)
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
api_key=os.environ["CARTESIA_API_KEY"],
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
api_key=os.environ["OPENAI_API_KEY"],
settings=OpenAILLMService.Settings(
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
),

6
examples/voice/voice-assemblyai.py
View File

@@ -54,18 +54,18 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = AssemblyAISTTService(
api_key=os.getenv("ASSEMBLYAI_API_KEY"),
api_key=os.environ["ASSEMBLYAI_API_KEY"],
)
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
api_key=os.environ["CARTESIA_API_KEY"],
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
api_key=os.environ["OPENAI_API_KEY"],
settings=OpenAILLMService.Settings(
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
),

4
examples/voice/voice-asyncai-http.py
View File

@@ -56,7 +56,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
# Create an HTTP session
async with aiohttp.ClientSession() as session:
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
tts = AsyncAIHttpTTSService(
api_key=os.getenv("ASYNCAI_API_KEY", ""),
@@ -67,7 +67,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
api_key=os.environ["OPENAI_API_KEY"],
settings=OpenAILLMService.Settings(
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
),

4
examples/voice/voice-asyncai.py
View File

@@ -53,7 +53,7 @@ transport_params = {
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
tts = AsyncAITTSService(
api_key=os.getenv("ASYNCAI_API_KEY", ""),
@@ -63,7 +63,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
api_key=os.environ["OPENAI_API_KEY"],
settings=OpenAILLMService.Settings(
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
),

10
examples/voice/voice-azure-http.py
View File

@@ -53,18 +53,18 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = AzureSTTService(
api_key=os.getenv("AZURE_SPEECH_API_KEY"),
api_key=os.environ["AZURE_SPEECH_API_KEY"],
region=os.getenv("AZURE_SPEECH_REGION"),
)
tts = AzureHttpTTSService(
api_key=os.getenv("AZURE_SPEECH_API_KEY"),
region=os.getenv("AZURE_SPEECH_REGION"),
api_key=os.environ["AZURE_SPEECH_API_KEY"],
region=os.environ["AZURE_SPEECH_REGION"],
)
llm = AzureLLMService(
api_key=os.getenv("AZURE_CHATGPT_API_KEY"),
endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"),
api_key=os.environ["AZURE_CHATGPT_API_KEY"],
endpoint=os.environ["AZURE_CHATGPT_ENDPOINT"],
settings=AzureLLMService.Settings(
model=os.getenv("AZURE_CHATGPT_MODEL"),
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",

10
examples/voice/voice-azure.py
View File

@@ -53,18 +53,18 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = AzureSTTService(
api_key=os.getenv("AZURE_SPEECH_API_KEY"),
api_key=os.environ["AZURE_SPEECH_API_KEY"],
region=os.getenv("AZURE_SPEECH_REGION"),
)
tts = AzureTTSService(
api_key=os.getenv("AZURE_SPEECH_API_KEY"),
region=os.getenv("AZURE_SPEECH_REGION"),
api_key=os.environ["AZURE_SPEECH_API_KEY"],
region=os.environ["AZURE_SPEECH_REGION"],
)
llm = AzureLLMService(
api_key=os.getenv("AZURE_CHATGPT_API_KEY"),
endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"),
api_key=os.environ["AZURE_CHATGPT_API_KEY"],
endpoint=os.environ["AZURE_CHATGPT_ENDPOINT"],
settings=AzureLLMService.Settings(
model=os.getenv("AZURE_CHATGPT_MODEL"),
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",

6
examples/voice/voice-camb.py
View File

@@ -52,17 +52,17 @@ transport_params = {
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info("Starting Camb AI TTS bot")
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
tts = CambTTSService(
api_key=os.getenv("CAMB_API_KEY"),
api_key=os.environ["CAMB_API_KEY"],
settings=CambTTSService.Settings(
model="mars-flash",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
api_key=os.environ["OPENAI_API_KEY"],
settings=OpenAILLMService.Settings(
system_instruction="You are a helpful voice assistant powered by Camb AI text-to-speech. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Keep responses concise.",
),

6
examples/voice/voice-cartesia-http.py
View File

@@ -54,10 +54,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
async with aiohttp.ClientSession() as session:
stt = CartesiaSTTService(api_key=os.getenv("CARTESIA_API_KEY"))
stt = CartesiaSTTService(api_key=os.environ["CARTESIA_API_KEY"])
tts = CartesiaHttpTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
api_key=os.environ["CARTESIA_API_KEY"],
aiohttp_session=session,
settings=CartesiaHttpTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
@@ -65,7 +65,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
api_key=os.environ["OPENAI_API_KEY"],
settings=OpenAILLMService.Settings(
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
),

6
examples/voice/voice-cartesia.py
View File

@@ -51,17 +51,17 @@ transport_params = {
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = CartesiaSTTService(api_key=os.getenv("CARTESIA_API_KEY"))
stt = CartesiaSTTService(api_key=os.environ["CARTESIA_API_KEY"])
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
api_key=os.environ["CARTESIA_API_KEY"],
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
api_key=os.environ["OPENAI_API_KEY"],
settings=OpenAILLMService.Settings(
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
),

8
examples/voice/voice-deepgram-flux-sagemaker.py
View File

@@ -59,8 +59,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
# - AWS credentials configured (via environment variables or AWS CLI)
# - A deployed SageMaker endpoint with Deepgram Flux model
stt = DeepgramFluxSageMakerSTTService(
endpoint_name=os.getenv("SAGEMAKER_STT_ENDPOINT_NAME"),
region=os.getenv("AWS_REGION"),
endpoint_name=os.environ["SAGEMAKER_STT_ENDPOINT_NAME"],
region=os.environ["AWS_REGION"],
settings=DeepgramFluxSageMakerSTTService.Settings(
min_confidence=0.3,
),
@@ -71,8 +71,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
# - AWS credentials configured (via environment variables or AWS CLI)
# - A deployed SageMaker endpoint with Deepgram TTS model
tts = DeepgramSageMakerTTSService(
endpoint_name=os.getenv("SAGEMAKER_TTS_ENDPOINT_NAME"),
region=os.getenv("AWS_REGION"),
endpoint_name=os.environ["SAGEMAKER_TTS_ENDPOINT_NAME"],
region=os.environ["AWS_REGION"],
settings=DeepgramSageMakerTTSService.Settings(
voice="aura-2-andromeda-en",
),

6
examples/voice/voice-deepgram-flux.py
View File

@@ -55,21 +55,21 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = DeepgramFluxSTTService(
api_key=os.getenv("DEEPGRAM_API_KEY"),
api_key=os.environ["DEEPGRAM_API_KEY"],
settings=DeepgramFluxSTTService.Settings(
min_confidence=0.3,
),
)
tts = DeepgramTTSService(
api_key=os.getenv("DEEPGRAM_API_KEY"),
api_key=os.environ["DEEPGRAM_API_KEY"],
settings=DeepgramTTSService.Settings(
voice="aura-2-andromeda-en",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
api_key=os.environ["OPENAI_API_KEY"],
settings=OpenAILLMService.Settings(
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
),

6
examples/voice/voice-deepgram-http.py
View File

@@ -55,10 +55,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
async with aiohttp.ClientSession() as session:
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
tts = DeepgramHttpTTSService(
api_key=os.getenv("DEEPGRAM_API_KEY"),
api_key=os.environ["DEEPGRAM_API_KEY"],
settings=DeepgramHttpTTSService.Settings(
voice="aura-2-andromeda-en",
),
@@ -66,7 +66,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
api_key=os.environ["OPENAI_API_KEY"],
settings=OpenAILLMService.Settings(
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
),

8
examples/voice/voice-deepgram-sagemaker.py
View File

@@ -58,8 +58,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
# - AWS credentials configured (via environment variables or AWS CLI)
# - A deployed SageMaker endpoint with Deepgram model
stt = DeepgramSageMakerSTTService(
endpoint_name=os.getenv("SAGEMAKER_STT_ENDPOINT_NAME"),
region=os.getenv("AWS_REGION"),
endpoint_name=os.environ["SAGEMAKER_STT_ENDPOINT_NAME"],
region=os.environ["AWS_REGION"],
)
# Initialize Deepgram SageMaker TTS Service
@@ -67,8 +67,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
# - AWS credentials configured (via environment variables or AWS CLI)
# - A deployed SageMaker endpoint with Deepgram TTS model
tts = DeepgramSageMakerTTSService(
endpoint_name=os.getenv("SAGEMAKER_TTS_ENDPOINT_NAME"),
region=os.getenv("AWS_REGION"),
endpoint_name=os.environ["SAGEMAKER_TTS_ENDPOINT_NAME"],
region=os.environ["AWS_REGION"],
settings=DeepgramSageMakerTTSService.Settings(
voice="aura-2-andromeda-en",
),

133
examples/voice/voice-deepgram-vad.py
View File

@@ -1,133 +0,0 @@
#
# Copyright (c) 2024-2026, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
import os
from dotenv import load_dotenv
from loguru import logger
from pipecat.frames.frames import LLMRunFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.aggregators.llm_context import LLMContext
from pipecat.processors.aggregators.llm_response_universal import (
LLMContextAggregatorPair,
LLMUserAggregatorParams,
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.deepgram.tts import DeepgramTTSService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
from pipecat.turns.user_turn_strategies import ExternalUserTurnStrategies
load_dotenv(override=True)
# We use lambdas to defer transport parameter creation until the transport
# type is selected at runtime.
transport_params = {
"daily": lambda: DailyParams(
audio_in_enabled=True,
audio_out_enabled=True,
),
"twilio": lambda: FastAPIWebsocketParams(
audio_in_enabled=True,
audio_out_enabled=True,
),
"webrtc": lambda: TransportParams(
audio_in_enabled=True,
audio_out_enabled=True,
),
}
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = DeepgramSTTService(
api_key=os.getenv("DEEPGRAM_API_KEY"),
settings=DeepgramSTTService.Settings(
vad_events=True,
utterance_end_ms="1000",
),
)
tts = DeepgramTTSService(
api_key=os.getenv("DEEPGRAM_API_KEY"),
settings=DeepgramTTSService.Settings(
voice="aura-2-andromeda-en",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMService.Settings(
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
),
)
context = LLMContext()
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
context,
user_params=LLMUserAggregatorParams(user_turn_strategies=ExternalUserTurnStrategies()),
)
pipeline = Pipeline(
[
transport.input(), # Transport user input
stt, # STT
user_aggregator, # User responses
llm, # LLM
tts, # TTS
transport.output(), # Transport bot output
assistant_aggregator, # Assistant spoken responses
]
)
task = PipelineTask(
pipeline,
params=PipelineParams(
enable_metrics=True,
enable_usage_metrics=True,
),
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
)
@transport.event_handler("on_client_connected")
async def on_client_connected(transport, client):
logger.info(f"Client connected")
# Kick off the conversation.
context.add_message(
{"role": "developer", "content": "Please introduce yourself to the user."}
)
await task.queue_frames([LLMRunFrame()])
@transport.event_handler("on_client_disconnected")
async def on_client_disconnected(transport, client):
logger.info(f"Client disconnected")
await task.cancel()
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
await runner.run(task)
async def bot(runner_args: RunnerArguments):
"""Main bot entry point compatible with Pipecat Cloud."""
transport = await create_transport(runner_args, transport_params)
await run_bot(transport, runner_args)
if __name__ == "__main__":
from pipecat.runner.run import main
main()

6
examples/voice/voice-deepgram.py
View File

@@ -53,17 +53,17 @@ transport_params = {
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
tts = DeepgramTTSService(
api_key=os.getenv("DEEPGRAM_API_KEY"),
api_key=os.environ["DEEPGRAM_API_KEY"],
settings=DeepgramTTSService.Settings(
voice="aura-2-andromeda-en",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
api_key=os.environ["OPENAI_API_KEY"],
settings=OpenAILLMService.Settings(
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
),

4
examples/voice/voice-elevenlabs-http.py
View File

@@ -57,7 +57,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
# Create an HTTP session
async with aiohttp.ClientSession() as session:
stt = ElevenLabsSTTService(
api_key=os.getenv("ELEVENLABS_API_KEY"),
api_key=os.environ["ELEVENLABS_API_KEY"],
aiohttp_session=session,
)
@@ -70,7 +70,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
api_key=os.environ["OPENAI_API_KEY"],
settings=OpenAILLMService.Settings(
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
),

4
examples/voice/voice-elevenlabs.py
View File

@@ -53,7 +53,7 @@ transport_params = {
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = ElevenLabsRealtimeSTTService(api_key=os.getenv("ELEVENLABS_API_KEY"))
stt = ElevenLabsRealtimeSTTService(api_key=os.environ["ELEVENLABS_API_KEY"])
tts = ElevenLabsTTSService(
api_key=os.getenv("ELEVENLABS_API_KEY", ""),
@@ -63,7 +63,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
api_key=os.environ["OPENAI_API_KEY"],
settings=OpenAILLMService.Settings(
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
),

4
examples/voice/voice-fal.py
View File

@@ -61,14 +61,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
)
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
api_key=os.environ["CARTESIA_API_KEY"],
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
api_key=os.environ["OPENAI_API_KEY"],
settings=OpenAILLMService.Settings(
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
),

6
examples/voice/voice-fish.py
View File

@@ -53,17 +53,17 @@ transport_params = {
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
tts = FishAudioTTSService(
api_key=os.getenv("FISH_API_KEY"),
api_key=os.environ["FISH_API_KEY"],
settings=FishAudioTTSService.Settings(
voice="4ce7e917cedd4bc2bb2e6ff3a46acaa1", # Barack Obama
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
api_key=os.environ["OPENAI_API_KEY"],
settings=OpenAILLMService.Settings(
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
),

7
examples/voice/voice-gladia-vad.py
View File

@@ -55,9 +55,12 @@ transport_params = {
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
region = os.getenv("GLADIA_REGION", "us-west")
assert region in ("us-west", "eu-west"), f"Invalid GLADIA_REGION: {region}"
stt = GladiaSTTService(
api_key=os.getenv("GLADIA_API_KEY", ""),
region=os.getenv("GLADIA_REGION"),
api_key=os.environ["GLADIA_API_KEY"],
region=region,
settings=GladiaSTTService.Settings(
language_config=LanguageConfig(
languages=[Language.EN],

7
examples/voice/voice-gladia.py
View File

@@ -54,9 +54,12 @@ transport_params = {
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
region = os.getenv("GLADIA_REGION", "us-west")
assert region in ("us-west", "eu-west"), f"Invalid GLADIA_REGION: {region}"
stt = GladiaSTTService(
api_key=os.getenv("GLADIA_API_KEY", ""),
region=os.getenv("GLADIA_REGION"),
api_key=os.environ["GLADIA_API_KEY"],
region=region,
settings=GladiaSTTService.Settings(
language_config=LanguageConfig(
languages=[Language.EN],

4
examples/voice/voice-google-audio-in.py
View File

@@ -215,7 +215,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
llm = GoogleLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
api_key=os.environ["GOOGLE_API_KEY"],
settings=GoogleLLMService.Settings(
model="gemini-2.5-flash",
system_instruction=system_message,
@@ -230,7 +230,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
language=Language.EN_US,
),
params=GoogleTTSService.InputParams(language=Language.EN_US),
credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
credentials=os.environ["GOOGLE_TEST_CREDENTIALS"],
)
context = LLMContext()

6
examples/voice/voice-google-gemini-tts.py
View File

@@ -57,11 +57,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
settings=GoogleSTTService.Settings(
languages=[Language.EN_US],
),
credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
credentials=os.environ["GOOGLE_TEST_CREDENTIALS"],
)
tts = GeminiTTSService(
credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
credentials=os.environ["GOOGLE_TEST_CREDENTIALS"],
settings=GeminiTTSService.Settings(
model="gemini-2.5-flash-tts",
voice="Charon",
@@ -71,7 +71,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
)
llm = GoogleLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
api_key=os.environ["GOOGLE_API_KEY"],
model="gemini-2.5-flash",
settings=GoogleLLMService.Settings(
system_instruction="""You are a helpful assistant in a voice conversation.

6
examples/voice/voice-google-http.py
View File

@@ -59,7 +59,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
# Add model to use a specific model
# model="chirp_3",
),
credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
credentials=os.environ["GOOGLE_TEST_CREDENTIALS"],
location="us",
)
@@ -68,11 +68,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
voice="en-US-Chirp3-HD-Charon",
language=Language.EN_US,
),
credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
credentials=os.environ["GOOGLE_TEST_CREDENTIALS"],
)
llm = GoogleLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
api_key=os.environ["GOOGLE_API_KEY"],
settings=GoogleLLMService.Settings(
model="gemini-2.5-flash",
# force a certain amount of thinking if you want it

6
examples/voice/voice-google-image.py
View File

@@ -67,14 +67,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = GoogleSTTService(
credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
credentials=os.environ["GOOGLE_TEST_CREDENTIALS"],
settings=GoogleSTTService.Settings(
languages=[Language.EN_US],
),
)
tts = GoogleTTSService(
credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
credentials=os.environ["GOOGLE_TEST_CREDENTIALS"],
settings=GoogleTTSService.Settings(
voice="en-US-Chirp3-HD-Charon",
language=Language.EN_US,
@@ -82,7 +82,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
)
llm = GoogleLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
api_key=os.environ["GOOGLE_API_KEY"],
settings=GoogleLLMService.Settings(
model="gemini-2.5-flash-image",
# model="gemini-3-pro-image-preview", # A more powerful model, but slower,

6
examples/voice/voice-google.py
View File

@@ -59,7 +59,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
# Add model to use a specific model
# model="chirp_3",
),
credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
credentials=os.environ["GOOGLE_TEST_CREDENTIALS"],
location="us",
)
@@ -68,11 +68,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
voice="en-US-Chirp3-HD-Charon",
language=Language.EN_US,
),
credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
credentials=os.environ["GOOGLE_TEST_CREDENTIALS"],
)
llm = GoogleLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
api_key=os.environ["GOOGLE_API_KEY"],
settings=GoogleLLMService.Settings(
model="gemini-2.5-flash",
# force a certain amount of thinking if you want it

6
examples/voice/voice-gradium.py
View File

@@ -53,7 +53,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = GradiumSTTService(
api_key=os.getenv("GRADIUM_API_KEY"),
api_key=os.environ["GRADIUM_API_KEY"],
api_endpoint_base_url="wss://us.api.gradium.ai/api/speech/asr",
settings=GradiumSTTService.Settings(
language=Language.EN,
@@ -61,7 +61,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
)
tts = GradiumTTSService(
api_key=os.getenv("GRADIUM_API_KEY"),
api_key=os.environ["GRADIUM_API_KEY"],
url="wss://us.api.gradium.ai/api/speech/tts",
settings=GradiumTTSService.Settings(
voice="YTpq7expH9539ERJ",
@@ -69,7 +69,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
api_key=os.environ["OPENAI_API_KEY"],
settings=OpenAILLMService.Settings(
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
),

6
examples/voice/voice-groq.py
View File

@@ -52,17 +52,17 @@ transport_params = {
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = GroqSTTService(api_key=os.getenv("GROQ_API_KEY"))
stt = GroqSTTService(api_key=os.environ["GROQ_API_KEY"])
llm = GroqLLMService(
api_key=os.getenv("GROQ_API_KEY"),
api_key=os.environ["GROQ_API_KEY"],
settings=GroqLLMService.Settings(
model="llama-3.1-8b-instant",
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
),
)
tts = GroqTTSService(api_key=os.getenv("GROQ_API_KEY"))
tts = GroqTTSService(api_key=os.environ["GROQ_API_KEY"])
context = LLMContext()
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(

4
examples/voice/voice-hume.py
View File

@@ -54,7 +54,7 @@ transport_params = {
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
tts = HumeTTSService(
api_key=os.getenv("HUME_API_KEY"),
@@ -65,7 +65,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
api_key=os.environ["OPENAI_API_KEY"],
settings=OpenAILLMService.Settings(
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
),

4
examples/voice/voice-inworld-http.py
View File

@@ -53,7 +53,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info("Starting bot")
async with aiohttp.ClientSession() as session:
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
tts = InworldHttpTTSService(
api_key=os.getenv("INWORLD_API_KEY", ""),
@@ -66,7 +66,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
api_key=os.environ["OPENAI_API_KEY"],
settings=OpenAILLMService.Settings(
system_instruction="You are a helpful AI demonstrating Inworld AI's TTS. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a friendly and helpful way.",
),

4
examples/voice/voice-inworld.py
View File

@@ -50,7 +50,7 @@ transport_params = {
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info("Starting bot")
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
tts = InworldTTSService(
api_key=os.getenv("INWORLD_API_KEY", ""),
@@ -61,7 +61,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
api_key=os.environ["OPENAI_API_KEY"],
settings=OpenAILLMService.Settings(
system_instruction="You are a helpful AI demonstrating Inworld AI's TTS. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a friendly and helpful way.",
),

4
examples/voice/voice-kokoro.py
View File

@@ -52,7 +52,7 @@ transport_params = {
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
tts = KokoroTTSService(
settings=KokoroTTSService.Settings(
@@ -61,7 +61,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
api_key=os.environ["OPENAI_API_KEY"],
settings=OpenAILLMService.Settings(
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
),

6
examples/voice/voice-krisp-viva.py
View File

@@ -84,17 +84,17 @@ transport_params = {
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
api_key=os.environ["CARTESIA_API_KEY"],
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
api_key=os.environ["OPENAI_API_KEY"],
settings=OpenAILLMService.Settings(
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
),

12
examples/voice/voice-langchain.py
View File

@@ -16,7 +16,7 @@ from langchain_openai import ChatOpenAI
from loguru import logger
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import LLMMessagesUpdateFrame
from pipecat.frames.frames import LLMRunFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -67,10 +67,10 @@ transport_params = {
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
api_key=os.environ["CARTESIA_API_KEY"],
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
@@ -129,8 +129,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
# An `LLMContextFrame` will be picked up by the LangchainProcessor using
# only the content of the last message to inject it in the prompt defined
# above. So no role is required here.
messages = [({"content": "Please briefly introduce yourself to the user."})]
await task.queue_frames([LLMMessagesUpdateFrame(messages, run_llm=True)])
context.add_message(
{"role": "developer", "content": "Please briefly introduce yourself to the user."}
)
await task.queue_frames([LLMRunFrame()])
@transport.event_handler("on_client_disconnected")
async def on_client_disconnected(transport, client):

6
examples/voice/voice-lmnt.py
View File

@@ -52,17 +52,17 @@ transport_params = {
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
tts = LmntTTSService(
api_key=os.getenv("LMNT_API_KEY"),
api_key=os.environ["LMNT_API_KEY"],
settings=LmntTTSService.Settings(
voice="morgan",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
api_key=os.environ["OPENAI_API_KEY"],
settings=OpenAILLMService.Settings(
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
),

4
examples/voice/voice-minimax.py
View File

@@ -57,7 +57,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
# Create an HTTP session
async with aiohttp.ClientSession() as session:
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
tts = MiniMaxHttpTTSService(
api_key=os.getenv("MINIMAX_API_KEY", ""),
@@ -69,7 +69,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
api_key=os.environ["OPENAI_API_KEY"],
settings=OpenAILLMService.Settings(
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
),

6
examples/voice/voice-mistral.py
View File

@@ -53,17 +53,17 @@ transport_params = {
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = MistralSTTService(api_key=os.getenv("MISTRAL_API_KEY"))
stt = MistralSTTService(api_key=os.environ["MISTRAL_API_KEY"])
tts = MistralTTSService(
api_key=os.getenv("MISTRAL_API_KEY"),
api_key=os.environ["MISTRAL_API_KEY"],
settings=MistralTTSService.Settings(
voice="c69964a6-ab8b-4f8a-9465-ec0925096ec8",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
api_key=os.environ["OPENAI_API_KEY"],
settings=OpenAILLMService.Settings(
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
),

6
examples/voice/voice-neuphonic-http.py
View File

@@ -56,10 +56,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
# Create an HTTP session
async with aiohttp.ClientSession() as session:
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
tts = NeuphonicHttpTTSService(
api_key=os.getenv("NEUPHONIC_API_KEY"),
api_key=os.environ["NEUPHONIC_API_KEY"],
settings=NeuphonicHttpTTSService.Settings(
voice="fc854436-2dac-4d21-aa69-ae17b54e98eb", # Emily
),
@@ -67,7 +67,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
api_key=os.environ["OPENAI_API_KEY"],
settings=OpenAILLMService.Settings(
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
),

6
examples/voice/voice-neuphonic.py
View File

@@ -52,17 +52,17 @@ transport_params = {
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
tts = NeuphonicTTSService(
api_key=os.getenv("NEUPHONIC_API_KEY"),
api_key=os.environ["NEUPHONIC_API_KEY"],
settings=NeuphonicTTSService.Settings(
voice="fc854436-2dac-4d21-aa69-ae17b54e98eb", # Emily
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
api_key=os.environ["OPENAI_API_KEY"],
settings=OpenAILLMService.Settings(
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
),

6
examples/voice/voice-nvidia.py
View File

@@ -52,17 +52,17 @@ transport_params = {
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = NvidiaSTTService(api_key=os.getenv("NVIDIA_API_KEY"))
stt = NvidiaSTTService(api_key=os.environ["NVIDIA_API_KEY"])
llm = NvidiaLLMService(
api_key=os.getenv("NVIDIA_API_KEY"),
api_key=os.environ["NVIDIA_API_KEY"],
settings=NvidiaLLMService.Settings(
model="meta/llama-3.3-70b-instruct",
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
),
)
tts = NvidiaTTSService(api_key=os.getenv("NVIDIA_API_KEY"))
tts = NvidiaTTSService(api_key=os.environ["NVIDIA_API_KEY"])
context = LLMContext()
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(

6
examples/voice/voice-openai-http.py
View File

@@ -53,7 +53,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = OpenAISTTService(
api_key=os.getenv("OPENAI_API_KEY"),
api_key=os.environ["OPENAI_API_KEY"],
settings=OpenAISTTService.Settings(
model="gpt-4o-transcribe",
prompt="Expect words related to dogs, such as breed names.",
@@ -61,14 +61,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
)
tts = OpenAITTSService(
api_key=os.getenv("OPENAI_API_KEY"),
api_key=os.environ["OPENAI_API_KEY"],
settings=OpenAITTSService.Settings(
voice="ballad",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
api_key=os.environ["OPENAI_API_KEY"],
settings=OpenAILLMService.Settings(
system_instruction="You are very knowledgable about dogs. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
),

6
examples/voice/voice-openai-responses-http.py
View File

@@ -51,17 +51,17 @@ transport_params = {
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
api_key=os.environ["CARTESIA_API_KEY"],
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAIResponsesHttpLLMService(
api_key=os.getenv("OPENAI_API_KEY"),
api_key=os.environ["OPENAI_API_KEY"],
settings=OpenAIResponsesHttpLLMService.Settings(
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
),

6
examples/voice/voice-openai-responses.py
View File

@@ -51,17 +51,17 @@ transport_params = {
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
api_key=os.environ["CARTESIA_API_KEY"],
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAIResponsesLLMService(
api_key=os.getenv("OPENAI_API_KEY"),
api_key=os.environ["OPENAI_API_KEY"],
settings=OpenAIResponsesLLMService.Settings(
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
),

6
examples/voice/voice-openai.py
View File

@@ -54,7 +54,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = OpenAIRealtimeSTTService(
api_key=os.getenv("OPENAI_API_KEY"),
api_key=os.environ["OPENAI_API_KEY"],
settings=OpenAIRealtimeSTTService.Settings(
model="gpt-4o-transcribe",
prompt="Expect words related to dogs, such as breed names.",
@@ -63,14 +63,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
)
tts = OpenAITTSService(
api_key=os.getenv("OPENAI_API_KEY"),
api_key=os.environ["OPENAI_API_KEY"],
settings=OpenAITTSService.Settings(
voice="ballad",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
api_key=os.environ["OPENAI_API_KEY"],
settings=OpenAILLMService.Settings(
system_instruction="You are very knowledgable about dogs. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
),

4
examples/voice/voice-piper.py
View File

@@ -52,7 +52,7 @@ transport_params = {
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
tts = PiperTTSService(
settings=PiperTTSService.Settings(
@@ -61,7 +61,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
api_key=os.environ["OPENAI_API_KEY"],
settings=OpenAILLMService.Settings(
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
),

8
examples/voice/voice-resemble.py
View File

@@ -51,17 +51,17 @@ transport_params = {
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
tts = ResembleAITTSService(
api_key=os.getenv("RESEMBLE_API_KEY"),
api_key=os.environ["RESEMBLE_API_KEY"],
settings=ResembleAITTSService.Settings(
voice=os.getenv("RESEMBLE_VOICE_UUID"),
voice=os.environ["RESEMBLE_VOICE_UUID"],
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
api_key=os.environ["OPENAI_API_KEY"],
settings=OpenAILLMService.Settings(
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
),

4
examples/voice/voice-rime-http.py
View File

@@ -56,7 +56,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
# Create an HTTP session
async with aiohttp.ClientSession() as session:
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
tts = RimeHttpTTSService(
api_key=os.getenv("RIME_API_KEY", ""),
@@ -69,7 +69,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
api_key=os.environ["OPENAI_API_KEY"],
settings=OpenAILLMService.Settings(
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
),

4
examples/voice/voice-rime.py
View File

@@ -52,7 +52,7 @@ transport_params = {
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
tts = RimeTTSService(
api_key=os.getenv("RIME_API_KEY", ""),
@@ -62,7 +62,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
api_key=os.environ["OPENAI_API_KEY"],
settings=OpenAILLMService.Settings(
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
),

6
examples/voice/voice-sarvam-http.py
View File

@@ -58,14 +58,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
# Create an HTTP session
async with aiohttp.ClientSession() as session:
stt = SarvamSTTService(
api_key=os.getenv("SARVAM_API_KEY"),
api_key=os.environ["SARVAM_API_KEY"],
settings=SarvamSTTService.Settings(
model="saarika:v2.5",
),
)
tts = SarvamHttpTTSService(
api_key=os.getenv("SARVAM_API_KEY"),
api_key=os.environ["SARVAM_API_KEY"],
aiohttp_session=session,
settings=SarvamHttpTTSService.Settings(
language=Language.EN_IN,
@@ -73,7 +73,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
)
llm = SarvamLLMService(
api_key=os.getenv("SARVAM_API_KEY"),
api_key=os.environ["SARVAM_API_KEY"],
settings=SarvamLLMService.Settings(
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
),

6
examples/voice/voice-sarvam.py
View File

@@ -53,21 +53,21 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = SarvamSTTService(
api_key=os.getenv("SARVAM_API_KEY"),
api_key=os.environ["SARVAM_API_KEY"],
settings=SarvamSTTService.Settings(
model="saaras:v3",
),
)
tts = SarvamTTSService(
api_key=os.getenv("SARVAM_API_KEY"),
api_key=os.environ["SARVAM_API_KEY"],
settings=SarvamTTSService.Settings(
model="bulbul:v3",
voice="shubh",
),
)
llm = SarvamLLMService(
api_key=os.getenv("SARVAM_API_KEY"),
api_key=os.environ["SARVAM_API_KEY"],
settings=SarvamLLMService.Settings(
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
),

6
examples/voice/voice-smallest.py
View File

@@ -52,21 +52,21 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = SmallestSTTService(
api_key=os.getenv("SMALLEST_API_KEY"),
api_key=os.environ["SMALLEST_API_KEY"],
settings=SmallestSTTService.Settings(
language=Language.EN,
),
)
tts = SmallestTTSService(
api_key=os.getenv("SMALLEST_API_KEY"),
api_key=os.environ["SMALLEST_API_KEY"],
settings=SmallestTTSService.Settings(
voice="sophia",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
api_key=os.environ["OPENAI_API_KEY"],
settings=OpenAILLMService.Settings(
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
),

6
examples/voice/voice-soniox.py
View File

@@ -52,7 +52,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = SonioxSTTService(
api_key=os.getenv("SONIOX_API_KEY"),
api_key=os.environ["SONIOX_API_KEY"],
settings=SonioxSTTService.Settings(
# Add language hints to use a specific language
# Add strict mode to enforce the language hints
@@ -62,14 +62,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
)
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
api_key=os.environ["CARTESIA_API_KEY"],
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
api_key=os.environ["OPENAI_API_KEY"],
settings=OpenAILLMService.Settings(
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
),

6
examples/voice/voice-speechmatics-vad.py
View File

@@ -91,7 +91,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
async with aiohttp.ClientSession() as session:
stt = SpeechmaticsSTTService(
api_key=os.getenv("SPEECHMATICS_API_KEY"),
api_key=os.environ["SPEECHMATICS_API_KEY"],
settings=SpeechmaticsSTTService.Settings(
language=Language.EN,
turn_detection_mode=SpeechmaticsSTTService.TurnDetectionMode.ADAPTIVE,
@@ -102,7 +102,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
)
tts = SpeechmaticsTTSService(
api_key=os.getenv("SPEECHMATICS_API_KEY"),
api_key=os.environ["SPEECHMATICS_API_KEY"],
settings=SpeechmaticsTTSService.Settings(
voice="sarah",
),
@@ -110,7 +110,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
api_key=os.environ["OPENAI_API_KEY"],
settings=OpenAILLMService.Settings(
temperature=0.75,
system_instruction="You are a helpful British assistant called Sarah in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Always include punctuation in your responses. Give very short replies - do not give longer replies unless strictly necessary. Respond to what the user said in a concise, funny, creative and helpful way. Use `<Sn/>` tags to identify different speakers - do not use tags in your replies. Do not respond to speakers within `<PASSIVE/>` tags unless explicitly asked to.",

6
examples/voice/voice-speechmatics.py
View File

@@ -74,7 +74,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
async with aiohttp.ClientSession() as session:
stt = SpeechmaticsSTTService(
api_key=os.getenv("SPEECHMATICS_API_KEY"),
api_key=os.environ["SPEECHMATICS_API_KEY"],
settings=SpeechmaticsSTTService.Settings(
language=Language.EN,
speaker_active_format="<{speaker_id}>{text}</{speaker_id}>",
@@ -82,7 +82,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
)
tts = SpeechmaticsTTSService(
api_key=os.getenv("SPEECHMATICS_API_KEY"),
api_key=os.environ["SPEECHMATICS_API_KEY"],
settings=SpeechmaticsTTSService.Settings(
voice="sarah",
),
@@ -90,7 +90,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
api_key=os.environ["OPENAI_API_KEY"],
settings=OpenAILLMService.Settings(
temperature=0.75,
system_instruction="You are a helpful British assistant called Sarah in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Always include punctuation in your responses. Give very short replies - do not give longer replies unless strictly necessary. Respond to what the user said in a concise, funny, creative and helpful way. Use `<Sn/>` tags to identify different speakers - do not use tags in your replies. Do not respond to speakers within `<PASSIVE/>` tags unless explicitly asked to.",

6
examples/voice/voice-xai.py
View File

@@ -53,10 +53,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
async with aiohttp.ClientSession() as session:
stt = XAISTTService(api_key=os.getenv("XAI_API_KEY"))
stt = XAISTTService(api_key=os.environ["XAI_API_KEY"])
tts = XAIHttpTTSService(
api_key=os.getenv("XAI_API_KEY"),
api_key=os.environ["XAI_API_KEY"],
aiohttp_session=session,
settings=XAIHttpTTSService.Settings(
voice="eve",
@@ -64,7 +64,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
)
llm = GrokLLMService(
api_key=os.getenv("XAI_API_KEY"),
api_key=os.environ["XAI_API_KEY"],
settings=GrokLLMService.Settings(
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
),

4
examples/voice/voice-xtts.py
View File

@@ -55,7 +55,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
# Create an HTTP session
async with aiohttp.ClientSession() as session:
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
tts = XTTSService(
aiohttp_session=session,
@@ -66,7 +66,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
api_key=os.environ["OPENAI_API_KEY"],
settings=OpenAILLMService.Settings(
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
),